Add QTextMarkdownWriter, QTextEdit::markdown property etc.

A QTextDocument can now be written out in Markdown format.

- Add the QTextMarkdownWriter as a private class for now
- Add QTextDocument::toMarkdown()
- QTextDocumentWriter uses QTextMarkdownWriter if setFormat("markdown")
  is called or if the file suffix is .md or .mkd
- Add QTextEdit::toMarkdown() and the markdown property

[ChangeLog][QtGui][Text] Markdown (CommonMark or GitHub dialect) is now
a supported format for reading into and writing from QTextDocument.

Change-Id: I663a77017fac7ae1b3f9a400f5cd357bb40750af
Reviewed-by: Gatis Paeglis <gatis.paeglis@qt.io>

6 files changed, 506 insertions, 3 deletions

diff --git a/src/gui/text/qtextdocument.cpp b/src/gui/text/qtextdocument.cpp
index 87c8f1ba8a..0a59bfb838 100644
--- a/src/gui/text/qtextdocument.cpp
+++ b/src/gui/text/qtextdocument.cpp
@@ -73,6 +73,9 @@
 #if QT_CONFIG(textmarkdownreader)
 #include <private/qtextmarkdownimporter_p.h>
 #endif
+#if QT_CONFIG(textmarkdownwriter)
+#include <private/qtextmarkdownwriter_p.h>
+#endif
 
 #include <limits.h>
 
@@ -3289,6 +3292,22 @@ QString QTextDocument::toHtml(const QByteArray &encoding) const
 #endif // QT_NO_TEXTHTMLPARSER
 
 /*!
+    Returns a string containing a Markdown representation of the document,
+    or an empty string if writing fails for any reason.
+*/
+#if QT_CONFIG(textmarkdownwriter)
+QString QTextDocument::toMarkdown(QTextDocument::MarkdownFeatures features) const
+{
+    QString ret;
+    QTextStream s(&ret);
+    QTextMarkdownWriter w(s, features);
+    if (w.writeAll(*this))
+        return ret;
+    return QString();
+}
+#endif
+
+/*!
     Replaces the entire contents of the document with the given
     Markdown-formatted text in the \a markdown string, with the given
     \a features supported.  By default, all supported GitHub-style
@@ -3301,8 +3320,19 @@ QString QTextDocument::toHtml(const QByteArray &encoding) const
 
     Parsing of HTML included in the \a markdown string is handled in the same
     way as in \l setHtml; however, Markdown formatting inside HTML blocks is
-    not supported. The \c MarkdownNoHTML feature flag can be set to disable
-    HTML parsing.
+    not supported.
+
+    Some features of the parser can be enabled or disabled via the \a features
+    argument:
+
+    \value MarkdownNoHTML
+           Any HTML tags in the Markdown text will be discarded
+    \value MarkdownDialectCommonMark
+           The parser supports only the features standardized by CommonMark
+    \value MarkdownDialectGitHub
+           The parser supports the GitHub dialect
+
+    The default is \c MarkdownDialectGitHub.
 
     The undo/redo history is reset when this function is called.
 */
diff --git a/src/gui/text/qtextdocument.h b/src/gui/text/qtextdocument.h
index ade67999ad..31c06976a5 100644
--- a/src/gui/text/qtextdocument.h
+++ b/src/gui/text/qtextdocument.h
@@ -151,7 +151,7 @@ public:
     void setHtml(const QString &html);
 #endif
 
-#if QT_CONFIG(textmarkdownreader)
+#if QT_CONFIG(textmarkdownwriter) || QT_CONFIG(textmarkdownreader)
     // Must be in sync with QTextMarkdownImporter::Features, should be in sync with #define MD_FLAG_* in md4c
     enum MarkdownFeature {
         MarkdownNoHTML = 0x0020 | 0x0040,
@@ -160,7 +160,13 @@ public:
     };
     Q_DECLARE_FLAGS(MarkdownFeatures, MarkdownFeature)
     Q_FLAG(MarkdownFeatures)
+#endif
 
+#if QT_CONFIG(textmarkdownwriter)
+    QString toMarkdown(MarkdownFeatures features = MarkdownDialectGitHub) const;
+#endif
+
+#if QT_CONFIG(textmarkdownreader)
     void setMarkdown(const QString &markdown, MarkdownFeatures features = MarkdownDialectGitHub);
 #endif
 
diff --git a/src/gui/text/qtextdocumentwriter.cpp b/src/gui/text/qtextdocumentwriter.cpp
index 42e623153a..c82ff873cd 100644
--- a/src/gui/text/qtextdocumentwriter.cpp
+++ b/src/gui/text/qtextdocumentwriter.cpp
@@ -51,6 +51,9 @@
 
 #include "qtextdocumentfragment_p.h"
 #include "qtextodfwriter_p.h"
+#if QT_CONFIG(textmarkdownwriter)
+#include "qtextmarkdownwriter_p.h"
+#endif
 
 #include <algorithm>
 
@@ -267,6 +270,18 @@ bool QTextDocumentWriter::write(const QTextDocument *document)
     }
 #endif // QT_NO_TEXTODFWRITER
 
+#if QT_CONFIG(textmarkdownwriter)
+    if (format == "md" || format == "mkd" || format == "markdown") {
+        if (!d->device->isWritable() && !d->device->open(QIODevice::WriteOnly)) {
+            qWarning("QTextDocumentWriter::write: the device can not be opened for writing");
+            return false;
+        }
+        QTextStream s(d->device);
+        QTextMarkdownWriter writer(s, QTextDocument::MarkdownDialectGitHub);
+        return writer.writeAll(*document);
+    }
+#endif // textmarkdownwriter
+
 #ifndef QT_NO_TEXTHTMLPARSER
     if (format == "html" || format == "htm") {
         if (!d->device->isWritable() && ! d->device->open(QIODevice::WriteOnly)) {
@@ -348,6 +363,7 @@ QTextCodec *QTextDocumentWriter::codec() const
     \header \li Format    \li Description
     \row    \li plaintext \li Plain text
     \row    \li HTML      \li HyperText Markup Language
+    \row    \li markdown  \li Markdown (CommonMark or GitHub dialects)
     \row    \li ODF       \li OpenDocument Format
     \endtable
 
@@ -364,6 +380,9 @@ QList<QByteArray> QTextDocumentWriter::supportedDocumentFormats()
 #ifndef QT_NO_TEXTODFWRITER
     answer << "ODF";
 #endif // QT_NO_TEXTODFWRITER
+#if QT_CONFIG(textmarkdownwriter)
+    answer << "markdown";
+#endif
 
     std::sort(answer.begin(), answer.end());
     return answer;
diff --git a/src/gui/text/qtextmarkdownwriter.cpp b/src/gui/text/qtextmarkdownwriter.cpp
new file mode 100644
index 0000000000..c91248757a
--- /dev/null
+++ b/src/gui/text/qtextmarkdownwriter.cpp
@@ -0,0 +1,363 @@
+/****************************************************************************
+**
+** Copyright (C) 2019 The Qt Company Ltd.
+** Contact: https://www.qt.io/licensing/
+**
+** This file is part of the QtGui module of the Qt Toolkit.
+**
+** $QT_BEGIN_LICENSE:LGPL$
+** Commercial License Usage
+** Licensees holding valid commercial Qt licenses may use this file in
+** accordance with the commercial license agreement provided with the
+** Software or, alternatively, in accordance with the terms contained in
+** a written agreement between you and The Qt Company. For licensing terms
+** and conditions see https://www.qt.io/terms-conditions. For further
+** information use the contact form at https://www.qt.io/contact-us.
+**
+** GNU Lesser General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU Lesser
+** General Public License version 3 as published by the Free Software
+** Foundation and appearing in the file LICENSE.LGPL3 included in the
+** packaging of this file. Please review the following information to
+** ensure the GNU Lesser General Public License version 3 requirements
+** will be met: https://www.gnu.org/licenses/lgpl-3.0.html.
+**
+** GNU General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU
+** General Public License version 2.0 or (at your option) the GNU General
+** Public license version 3 or any later version approved by the KDE Free
+** Qt Foundation. The licenses are as published by the Free Software
+** Foundation and appearing in the file LICENSE.GPL2 and LICENSE.GPL3
+** included in the packaging of this file. Please review the following
+** information to ensure the GNU General Public License requirements will
+** be met: https://www.gnu.org/licenses/gpl-2.0.html and
+** https://www.gnu.org/licenses/gpl-3.0.html.
+**
+** $QT_END_LICENSE$
+**
+****************************************************************************/
+
+#include "qtextmarkdownwriter_p.h"
+#include "qtextdocumentlayout_p.h"
+#include "qfontinfo.h"
+#include "qfontmetrics.h"
+#include "qtextdocument_p.h"
+#include "qtextlist.h"
+#include "qtexttable.h"
+#include "qtextcursor.h"
+#include "qtextimagehandler_p.h"
+
+QT_BEGIN_NAMESPACE
+
+static const QChar Space = QLatin1Char(' ');
+static const QChar Newline = QLatin1Char('\n');
+static const QChar Backtick = QLatin1Char('`');
+
+QTextMarkdownWriter::QTextMarkdownWriter(QTextStream &stream, QTextDocument::MarkdownFeatures features)
+  : m_stream(stream), m_features(features)
+{
+}
+
+bool QTextMarkdownWriter::writeAll(const QTextDocument &document)
+{
+    writeFrame(document.rootFrame());
+    return true;
+}
+
+void QTextMarkdownWriter::writeFrame(const QTextFrame *frame)
+{
+    Q_ASSERT(frame);
+    const QTextTable *table = qobject_cast<const QTextTable*> (frame);
+    QTextFrame::iterator iterator = frame->begin();
+    QTextFrame *child = 0;
+    int tableRow = -1;
+    bool lastWasList = false;
+    QVector<int> tableColumnWidths;
+    if (table) {
+        tableColumnWidths.resize(table->columns());
+        for (int col = 0; col < table->columns(); ++col) {
+            for (int row = 0; row < table->rows(); ++ row) {
+                QTextTableCell cell = table->cellAt(row, col);
+                int cellTextLen = 0;
+                auto it = cell.begin();
+                while (it != cell.end()) {
+                    QTextBlock block = it.currentBlock();
+                    if (block.isValid())
+                        cellTextLen += block.text().length();
+                    ++it;
+                }
+                if (cell.columnSpan() == 1 && tableColumnWidths[col] < cellTextLen)
+                    tableColumnWidths[col] = cellTextLen;
+            }
+        }
+    }
+    while (!iterator.atEnd()) {
+        if (iterator.currentFrame() && child != iterator.currentFrame())
+            writeFrame(iterator.currentFrame());
+        else { // no frame, it's a block
+            QTextBlock block = iterator.currentBlock();
+            if (table) {
+                QTextTableCell cell = table->cellAt(block.position());
+                if (tableRow < cell.row()) {
+                    if (tableRow == 0) {
+                        m_stream << Newline;
+                        for (int col = 0; col < tableColumnWidths.length(); ++col)
+                            m_stream << '|' << QString(tableColumnWidths[col], QLatin1Char('-'));
+                        m_stream << '|';
+                    }
+                    m_stream << Newline << "|";
+                    tableRow = cell.row();
+                }
+            } else if (!block.textList()) {
+                if (lastWasList)
+                    m_stream << Newline;
+            }
+            int endingCol = writeBlock(block, !table, table && tableRow == 0);
+            if (table) {
+                QTextTableCell cell = table->cellAt(block.position());
+                int paddingLen = -endingCol;
+                int spanEndCol = cell.column() + cell.columnSpan();
+                for (int col = cell.column(); col < spanEndCol; ++col)
+                    paddingLen += tableColumnWidths[col];
+                if (paddingLen > 0)
+                    m_stream << QString(paddingLen, Space);
+                for (int col = cell.column(); col < spanEndCol; ++col)
+                    m_stream << "|";
+            } else if (block.textList()) {
+                m_stream << Newline;
+            } else if (endingCol > 0) {
+                m_stream << Newline << Newline;
+            }
+            lastWasList = block.textList();
+        }
+        child = iterator.currentFrame();
+        ++iterator;
+    }
+    if (table)
+        m_stream << Newline << Newline;
+}
+
+static int nearestWordWrapIndex(const QString &s, int before)
+{
+    before = qMin(before, s.length());
+    for (int i = before - 1; i >= 0; --i) {
+        if (s.at(i).isSpace())
+            return i;
+    }
+    return -1;
+}
+
+static int adjacentBackticksCount(const QString &s)
+{
+    int start = -1, len = s.length();
+    int ret = 0;
+    for (int i = 0; i < len; ++i) {
+        if (s.at(i) == Backtick) {
+            if (start < 0)
+                start = i;
+        } else if (start >= 0) {
+            ret = qMax(ret, i - start);
+            start = -1;
+        }
+    }
+    if (s.at(len - 1) == Backtick)
+        ret = qMax(ret, len - start);
+    return ret;
+}
+
+static void maybeEscapeFirstChar(QString &s)
+{
+    QString sTrimmed = s.trimmed();
+    if (sTrimmed.isEmpty())
+        return;
+    char firstChar = sTrimmed.at(0).toLatin1();
+    if (firstChar == '*' || firstChar == '+' || firstChar == '-') {
+        int i = s.indexOf(QLatin1Char(firstChar));
+        s.insert(i, QLatin1Char('\\'));
+    }
+}
+
+int QTextMarkdownWriter::writeBlock(const QTextBlock &block, bool wrap, bool ignoreFormat)
+{
+    int ColumnLimit = 80;
+    int wrapIndent = 0;
+    if (block.textList()) { // it's a list-item
+        auto fmt = block.textList()->format();
+        const int listLevel = fmt.indent();
+        const int number = block.textList()->itemNumber(block) + 1;
+        QByteArray bullet = " ";
+        bool numeric = false;
+        switch (fmt.style()) {
+        case QTextListFormat::ListDisc: bullet = "-"; break;
+        case QTextListFormat::ListCircle: bullet = "*"; break;
+        case QTextListFormat::ListSquare: bullet = "+"; break;
+        case QTextListFormat::ListStyleUndefined: break;
+        case QTextListFormat::ListDecimal:
+        case QTextListFormat::ListLowerAlpha:
+        case QTextListFormat::ListUpperAlpha:
+        case QTextListFormat::ListLowerRoman:
+        case QTextListFormat::ListUpperRoman:
+            numeric = true;
+            break;
+        }
+        switch (block.blockFormat().marker()) {
+        case QTextBlockFormat::Checked:
+            bullet += " [x]";
+            break;
+        case QTextBlockFormat::Unchecked:
+            bullet += " [ ]";
+            break;
+        default:
+            break;
+        }
+        QString prefix((listLevel - 1) * (numeric ? 4 : 2), Space);
+        if (numeric)
+            prefix += QString::number(number) + fmt.numberSuffix() + Space;
+        else
+            prefix += QLatin1String(bullet) + Space;
+        m_stream << prefix;
+        wrapIndent = prefix.length();
+    }
+
+    if (block.blockFormat().headingLevel())
+        m_stream << QByteArray(block.blockFormat().headingLevel(), '#') << ' ';
+
+    QString wrapIndentString(wrapIndent, Space);
+    // It would be convenient if QTextStream had a lineCharPos() accessor,
+    // to keep track of how many characters (not bytes) have been written on the current line,
+    // but it doesn't.  So we have to keep track with this col variable.
+    int col = wrapIndent;
+    bool mono = false;
+    bool startsOrEndsWithBacktick = false;
+    bool bold = false;
+    bool italic = false;
+    bool underline = false;
+    bool strikeOut = false;
+    QString backticks(Backtick);
+    for (QTextBlock::Iterator frag = block.begin(); !frag.atEnd(); ++frag) {
+        QString fragmentText = frag.fragment().text();
+        while (fragmentText.endsWith(QLatin1Char('\n')))
+            fragmentText.chop(1);
+        startsOrEndsWithBacktick |= fragmentText.startsWith(Backtick) || fragmentText.endsWith(Backtick);
+        QTextCharFormat fmt = frag.fragment().charFormat();
+        if (fmt.isImageFormat()) {
+            QTextImageFormat ifmt = fmt.toImageFormat();
+            QString s = QLatin1String("![image](") + ifmt.name() + QLatin1Char(')');
+            if (wrap && col + s.length() > ColumnLimit) {
+                m_stream << Newline << wrapIndentString;
+                col = wrapIndent;
+            }
+            m_stream << s;
+            col += s.length();
+        } else if (fmt.hasProperty(QTextFormat::AnchorHref)) {
+            QString s = QLatin1Char('[') + fragmentText + QLatin1String("](") +
+                    fmt.property(QTextFormat::AnchorHref).toString() + QLatin1Char(')');
+            if (wrap && col + s.length() > ColumnLimit) {
+                m_stream << Newline << wrapIndentString;
+                col = wrapIndent;
+            }
+            m_stream << s;
+            col += s.length();
+        } else {
+            QFontInfo fontInfo(fmt.font());
+            bool monoFrag = fontInfo.fixedPitch();
+            QString markers;
+            if (!ignoreFormat) {
+                if (monoFrag != mono) {
+                    if (monoFrag)
+                        backticks = QString::fromLatin1(QByteArray(adjacentBackticksCount(fragmentText) + 1, '`'));
+                    markers += backticks;
+                    if (startsOrEndsWithBacktick)
+                        markers += Space;
+                    mono = monoFrag;
+                }
+                if (!block.blockFormat().headingLevel() && !mono) {
+                    if (fmt.font().bold() != bold) {
+                        markers += QLatin1String("**");
+                        bold = fmt.font().bold();
+                    }
+                    if (fmt.font().italic() != italic) {
+                        markers += QLatin1Char('*');
+                        italic = fmt.font().italic();
+                    }
+                    if (fmt.font().strikeOut() != strikeOut) {
+                        markers += QLatin1String("~~");
+                        strikeOut = fmt.font().strikeOut();
+                    }
+                    if (fmt.font().underline() != underline) {
+                        // Markdown doesn't support underline, but the parser will treat a single underline
+                        // the same as a single asterisk, and the marked fragment will be rendered in italics.
+                        // That will have to do.
+                        markers += QLatin1Char('_');
+                        underline = fmt.font().underline();
+                    }
+                }
+            }
+            if (wrap && col + markers.length() * 2 + fragmentText.length() > ColumnLimit) {
+                int i = 0;
+                int fragLen = fragmentText.length();
+                bool breakingLine = false;
+                while (i < fragLen) {
+                    int j = i + ColumnLimit - col;
+                    if (j < fragLen) {
+                        int wi = nearestWordWrapIndex(fragmentText, j);
+                        if (wi < 0) {
+                            j = fragLen;
+                        } else {
+                            j = wi;
+                            breakingLine = true;
+                        }
+                    } else {
+                        j = fragLen;
+                        breakingLine = false;
+                    }
+                    QString subfrag = fragmentText.mid(i, j - i);
+                    if (!i) {
+                        m_stream << markers;
+                        col += markers.length();
+                    }
+                    if (col == wrapIndent)
+                        maybeEscapeFirstChar(subfrag);
+                    m_stream << subfrag;
+                    if (breakingLine) {
+                        m_stream << Newline << wrapIndentString;
+                        col = wrapIndent;
+                    } else {
+                        col += subfrag.length();
+                    }
+                    i = j + 1;
+                }
+            } else {
+                m_stream << markers << fragmentText;
+                col += markers.length() + fragmentText.length();
+            }
+        }
+    }
+    if (mono) {
+        if (startsOrEndsWithBacktick) {
+            m_stream << Space;
+            col += 1;
+        }
+        m_stream << backticks;
+        col += backticks.size();
+    }
+    if (bold) {
+        m_stream << "**";
+        col += 2;
+    }
+    if (italic) {
+        m_stream << "*";
+        col += 1;
+    }
+    if (underline) {
+        m_stream << "_";
+        col += 1;
+    }
+    if (strikeOut) {
+        m_stream << "~~";
+        col += 2;
+    }
+    return col;
+}
+
+QT_END_NAMESPACE
diff --git a/src/gui/text/qtextmarkdownwriter_p.h b/src/gui/text/qtextmarkdownwriter_p.h
new file mode 100644
index 0000000000..9845355259
--- /dev/null
+++ b/src/gui/text/qtextmarkdownwriter_p.h
@@ -0,0 +1,78 @@
+/****************************************************************************
+**
+** Copyright (C) 2019 The Qt Company Ltd.
+** Contact: https://www.qt.io/licensing/
+**
+** This file is part of the QtGui module of the Qt Toolkit.
+**
+** $QT_BEGIN_LICENSE:LGPL$
+** Commercial License Usage
+** Licensees holding valid commercial Qt licenses may use this file in
+** accordance with the commercial license agreement provided with the
+** Software or, alternatively, in accordance with the terms contained in
+** a written agreement between you and The Qt Company. For licensing terms
+** and conditions see https://www.qt.io/terms-conditions. For further
+** information use the contact form at https://www.qt.io/contact-us.
+**
+** GNU Lesser General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU Lesser
+** General Public License version 3 as published by the Free Software
+** Foundation and appearing in the file LICENSE.LGPL3 included in the
+** packaging of this file. Please review the following information to
+** ensure the GNU Lesser General Public License version 3 requirements
+** will be met: https://www.gnu.org/licenses/lgpl-3.0.html.
+**
+** GNU General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU
+** General Public License version 2.0 or (at your option) the GNU General
+** Public license version 3 or any later version approved by the KDE Free
+** Qt Foundation. The licenses are as published by the Free Software
+** Foundation and appearing in the file LICENSE.GPL2 and LICENSE.GPL3
+** included in the packaging of this file. Please review the following
+** information to ensure the GNU General Public License requirements will
+** be met: https://www.gnu.org/licenses/gpl-2.0.html and
+** https://www.gnu.org/licenses/gpl-3.0.html.
+**
+** $QT_END_LICENSE$
+**
+****************************************************************************/
+
+#ifndef QTEXTMARKDOWNWRITER_P_H
+#define QTEXTMARKDOWNWRITER_P_H
+
+//
+//  W A R N I N G
+//  -------------
+//
+// This file is not part of the Qt API. It exists purely as an
+// implementation detail. This header file may change from version to
+// version without notice, or even be removed.
+//
+// We mean it.
+//
+
+#include <QtGui/private/qtguiglobal_p.h>
+#include <QtCore/QTextStream>
+
+#include "qtextdocument_p.h"
+#include "qtextdocumentwriter.h"
+
+QT_BEGIN_NAMESPACE
+
+class Q_GUI_EXPORT QTextMarkdownWriter
+{
+public:
+    QTextMarkdownWriter(QTextStream &stream, QTextDocument::MarkdownFeatures features);
+    bool writeAll(const QTextDocument &document);
+
+    int writeBlock(const QTextBlock &block, bool table, bool ignoreFormat);
+    void writeFrame(const QTextFrame *frame);
+
+private:
+    QTextStream &m_stream;
+    QTextDocument::MarkdownFeatures m_features;
+};
+
+QT_END_NAMESPACE
+
+#endif // QTEXTMARKDOWNWRITER_P_H
diff --git a/src/gui/text/text.pri b/src/gui/text/text.pri
index b35a231747..5e97b312f1 100644
--- a/src/gui/text/text.pri
+++ b/src/gui/text/text.pri
@@ -109,6 +109,13 @@ qtConfig(textmarkdownreader) {
         text/qtextmarkdownimporter.cpp
 }
 
+qtConfig(textmarkdownwriter) {
+    HEADERS += \
+        text/qtextmarkdownwriter_p.h
+    SOURCES += \
+        text/qtextmarkdownwriter.cpp
+}
+
 qtConfig(cssparser) {
     HEADERS += \
         text/qcssparser_p.h